Borrowing it
Nothing to install: this file belongs to hrygo/hotplex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hrygo/hotplex/main/AGENTS.mdgit clone --depth 1 https://github.com/hrygo/hotplexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/hrygo/hotplex/agents-md)<a href="https://agentmods.dev/instructions/hrygo/hotplex/agents-md"><img src="https://agentmods.dev/badge/instructions/hrygo/hotplex/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/hrygo/hotplex/agents-md"><img src="https://agentmods.dev/badge/instructions/hrygo/hotplex/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04779 | $0.04779 |
| Opus 5.5 | $0.01912 | $0.01912 |
| Sonnet 5.5 | $0.00956 | $0.00956 |
| Haiku 4.5 | $0.00478 | $0.00478 |
Grade A, and why
hotplex AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HotPlex 项目知识库
最后更新: 2026-10-09 · 分支: main · 版本: v1.52.0 · 提交: 4119b288
约定与规范
必须遵守
- Mutex: 显式
mu字段,不嵌入,不传指针 - 错误:
Err前缀(哨兵)、Error后缀(自定义)、fmt.Errorf("%w")包装 - 日志:
log/slogJSON handler(key 一律 snake_case,sloglint强制no-mixed-args) - 测试:
testify/require、table-driven、t.Parallel()、单模块 ≤5s(-count=1 -race -shuffle=on)、禁止time.Sleep等待异步结果(改用require.Eventually或 channel 信号) - Worker 注册:
init()+worker.Register()模式 - Worker 接口变更: 同步更新全部 adapter、测试 mock、
internal/worker/noop与registry_test;新增能力须明确其在 CLI、单例和 RPC Worker 上的语义 - AEP wire contract: 修改
pkg/events的 Kind、Data 或 JSON tag 时,同步更新 Go SDK、三种示例 SDK、docs/reference/{aep-protocol,events}.md与双向协议测试;新增字段必须向后兼容 - 持久化输入: Gateway 负责 accept → ACK → Worker 投递,
execution只保存 SHA-256 payload 指纹,绝不保存 prompt、metadata 值、凭证或原始 Worker 错误 - 数据库迁移: SQLite 与 PostgreSQL migration 必须成对新增;同步补 migration 与跨实例/条件更新测试,禁止只修一套方言
- 关闭顺序: signal → cancel ctx → tracing → hub → bridge → sessionMgr → HTTP
- 服务重启: 必须使用
hotplex service restart原子指令,禁止手动拆分stop && sleep && start(仅二进制替换场景需手动 stop 等待) - 非 main 分支 push: 非 main 分支本地验证通过后直接 commit + push,无需询问用户确认
- Git Hooks: clone 后必须安装 hooks(底层目标为
make hooks;pre-commit 跑 gofmt + golangci-lint,pre-push 跑完整质量门禁),禁止跳过;rtk可用时执行rtk proxy make hooks,不可用时执行原生make hooks并说明回退原因 - RTK 未过滤执行例外:以下规则仅适用于执行环境中可用
rtk(可用command -v rtk或rtk --version确认)。make docs-lint、make quality、make build、make hooks存在输出解析失败记录;rtk可用时必须分别通过rtk proxy make docs-lint、rtk proxy make quality、rtk proxy make build、rtk proxy make hooks执行,以保留原始诊断输出。rtk不可用时,允许执行对应的原生make命令,但必须说明未经过 RTK 过滤与统计;不得因本规则擅自安装 RTK。
反模式(禁止)
- ❌
sync.Mutex嵌入或传指针 - ❌
math/rand用于加密 - ❌ Shell 执行(仅允许
claude二进制) - ❌ 硬编码路径分隔符
- ❌ 直接使用 POSIX 信号
- ❌ 用
sed/awk插入或修改源码行(缩进不可控,必须用 Edit 工具)
代码编辑规则
- Edit 工具优先:修改源码必须使用 Edit 工具,禁止用
sed -i插入或修改代码行 - Edit 匹配失败时:重新 Read 文件获取精确内容,用精确字符串重试 Edit;扩大上下文使其唯一
- Go 文件 tab 缩进:Go 项目使用 tab 缩进(gofmt 标准)。使用 Edit 工具时,old_string 必须从 Read 输出中直接复制原文(保留 tab),禁止手敲空格缩进。Edit 匹配失败时先用
cat -A确认实际空白字符 sed适用场景:仅限非代码操作(config 快速替换、日志过滤等简单唯一 token 替换)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 18d ago Changed 0388f62b7a61
- 23d ago Changed · +1 tokens per session f3168dd0b6c0
- 1mo ago Changed · +6 lines · +196 tokens per session 3a7e03450937
- 1mo ago Changed · -2 tokens per session 578af0649a14
- 1mo ago Changed · +1 tokens per session b71b88987b84
- 1mo ago First seen · 204 lines · 4,583 tokens per session scan A 7289c2526c61
hotplex AGENTS.md is an instructions file published in the GitHub repository hrygo/hotplex (51 stars, last pushed 19d ago), licensed Apache-2.0. It adds 4,779 tokens to every session, about $0.0191 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.